© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 274
    Prev
    Next
    INDEX
    Explanations

    code and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    0.75
    ದ್ಧ
    0.73
    :“
    0.72
     Chairman
    0.71
    鍥
    0.70
    itudes
    0.70
    生日
    0.70
    嘈
    0.69
     Ajax
    0.68
    專輯
    0.68
    POSITIVE LOGITS
     seus
    0.86
     suoi
    0.86
     trabalhadores
    0.84
     vuelve
    0.82
     servidores
    0.81
     bekannt
    0.81
    <start_of_image>
    0.81
     voltou
    0.80
     conhecida
    0.78
     cunoscut
    0.78
    Activations Density 0.001%

    No Known Activations